Deep Learning-Based Human Activity Classification with OTFS Radar and Attention Enhanced LSTM Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26220%2F26%3A0199728" target="_blank" >RIV/00216305:26220/26:0199728 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/11351216" target="_blank" >https://ieeexplore.ieee.org/document/11351216</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/WPMC67460.2025.11351216" target="_blank" >10.1109/WPMC67460.2025.11351216</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep Learning-Based Human Activity Classification with OTFS Radar and Attention Enhanced LSTM Networks

Popis výsledku v původním jazyce

Radar-based human activity recognition (HAR) is emerging as a resilient alternative to camera systems in industrial environments, where occlusions, reflective surfaces, and privacy concerns limit vision-based methods. This paper presents a deep learning framework that integrates convolutional feature extraction, denoising, multi-head attention, and bidirectional LSTM layers to classify activities from OTFS radar delay–Doppler signatures. Experiments in cluttered industrial environments demonstrate that denoising improves robustness against clutter, while attention stabilizes performance across longer temporal sequences. With a sequence length of 50 frames and 32 attention heads, the proposed model achieves 95.2% accuracy on unseen test data. Visualization using t-SNE confirms clear activity separation, with minor overlap between walking and multi-person walking due to shared Doppler patterns. These results highlight the effectiveness of combining OTFS radar with attention-based temporal modeling for reliable and efficient HAR in real-world industrial monitoring.

Název v anglickém jazyce

Deep Learning-Based Human Activity Classification with OTFS Radar and Attention Enhanced LSTM Networks

Popis výsledku anglicky

Radar-based human activity recognition (HAR) is emerging as a resilient alternative to camera systems in industrial environments, where occlusions, reflective surfaces, and privacy concerns limit vision-based methods. This paper presents a deep learning framework that integrates convolutional feature extraction, denoising, multi-head attention, and bidirectional LSTM layers to classify activities from OTFS radar delay–Doppler signatures. Experiments in cluttered industrial environments demonstrate that denoising improves robustness against clutter, while attention stabilizes performance across longer temporal sequences. With a sequence length of 50 frames and 32 attention heads, the proposed model achieves 95.2% accuracy on unseen test data. Visualization using t-SNE confirms clear activity separation, with minor overlap between walking and multi-person walking due to shared Doppler patterns. These results highlight the effectiveness of combining OTFS radar with attention-based temporal modeling for reliable and efficient HAR in real-world industrial monitoring.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20202 - Communication engineering and systems

Projekt

<a href="/cs/project/LUC24141" target="_blank" >LUC24141: Simultánní komunikace a snímání pro zvyšování robustnosti systémů 6G</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 28th International Symposium on Wireless Personal Multimedia Communications (WPMC)

ISBN

979-8-3315-9128-1

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

—

Název nakladatele

IEEE

Místo vydání

Sofia, Bulgaria

Místo konání akce

Sofia, Bulgaria

Datum konání akce

9. 11. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—